PodcastIntel
Sign in Get Started Free
Latent Space: The AI Engineer Podcast

Latent Space: The AI Engineer Podcast

Alessio Fanelli · Technology · EN

This podcast explores the technical infrastructure, models, and agents used by leading AI labs, with a focus on AI for science. It features in-depth discussions with prominent AI engineers and researchers. The show is geared towards individuals interested in the practical engineering aspects of...

198
Episodes
89
Guests

Episodes (Page 6)

Dec 2, 2024 · 1h 38m
Bolt.new (by Stackblitz) surpasses $8M ARR in just 2 months as Claude wrapper, demonstrating explosive growth of vibe coding platforms alongside flow engineering for code agents
1h 38m
Nov 28, 2024 · 1h 11m
Erik Schluntz from Anthropic discusses new Claude 3.5 Sonnet capabilities, computer use features, and building state-of-the-art agents with latest model
Erik Schluntz
1h 11m
Nov 25, 2024 · 58m
Discussion of compound AI systems and open source advantages versus closed AI models in competitive landscape
58m
Nov 15, 2024 · 1h 9m
Lindy.ai founder Flo Crivello discusses agent platform evolution from late 2022 to present, challenging conventional wisdom in agent design with Rails and structured workflows
1h 9m
Nov 11, 2024 · 1h 0m
Stanislas from Dust discusses evolution of agent frameworks since LangChain vs Dust debate; Dust prioritizes practical agent workflows at enterprises
1h 0m
Nov 1, 2024 · 41m
LMSys Chatbot Arena leads Anastasios Angelopoulos and Wei-Lin Chiang discuss crowdsourced AI evaluation platform attracting 1M+ votes, becoming de facto LLM comparison standard
41m
Oct 25, 2024 · 1h 13m
NotebookLM's Audio Overviews feature converts documents, websites, and videos into conversational podcasts using voice models, RAG, and GPT, pioneered by PMs Raiza Martin and Usama Bin Shafqat
1h 13m
Oct 19, 2024 · 56m
Singapore's GovTech is hosting an AI CTF challenge with ~$15,000 in prizes starting October 26th on Dreadnode's Crucible platform, open to local and virtual hackers
Josephine Teo
56m
Oct 18, 2024 · 1h 11m
Drew Houston has spent 400+ hours coding with LLMs and is refocusing Dropbox's 2,500+ employees around AI-native development 17 years after founding the company
1h 11m
Oct 11, 2024 · 1h 56m
Ankur Goyal of Braintrust argues that production AI engineering should start with evals, not operational tooling, following the pattern of successful LLMOps founders with AI/research backgrounds
1h 56m
Oct 3, 2024 · 2h 9m
OpenAI DevDay 2024 focused on developer-facing API announcements including Realtime API, Vision Finetuning, Prompt Caching, and Model Distillation rather than ChatGPT product announcements
2h 9m
Sep 27, 2024 · 1h 29m
OpenAI's o1 release and recent hiring of Noam Brown and Shunyu Yao signals focus on tool-using chain-of-thought and tree-of-thought architectures for Level 3 Agents
1h 29m
Sep 20, 2024 · 1h 9m
Sander Schulhoff's 'The Prompt Report' synthesizes 1,600+ arXiv papers on prompting techniques including few-shot learning, chain-of-thought, tree search, and self-criticism strategies
1h 9m
Sep 13, 2024 · 2h 4m
Michelle Pokrass and OpenAI's DevRel team cover the entire OpenAI product suite including ChatGPT-latest, GPT-4o, o1 models, and how they're delivered via API with Structured Outputs
Michelle Pokrass
2h 4m
Sep 3, 2024 · 1h 5m
AI inference costs decreased 10-100x in 2024, with open models like Llama 3.1 405B costing $3/mtok versus $30/mtok for Claude 3 Opus, and frontier models dropped 400x from 2022-2024
1h 5m
Aug 29, 2024 · 1h 10m
Nicholas Carlini's 'How I Use AI' blog post demonstrates a practical approach focused on individual AI applications rather than broad AGI potential, covering 12 use cases with specific prompts
Nicholas Carlini
1h 10m
Aug 22, 2024 · 1h 5m
Cosine Genie achieved #1 ranking on SWE-Bench Full, Lite, and Verified using GPT-4o fine-tuning at scale on billions of tokens of synthetic data, beating all other agents including Cognition's Devin
Alistair Pullen
1h 5m
Aug 16, 2024 · 58m
Jeremy Howard's Answer.AI ships 1000s of successful AI products with no managers and a team of 12, focusing on practical AI R&D aligned with GPU-poor needs
58m
Aug 7, 2024 · 1h 3m
Meta's Segment Anything 2 (SAM 2) improves image segmentation accuracy while being 6x faster than SAM 1, and elegantly solved video segmentation with 3x fewer interactions than prior approaches
1h 3m
Aug 2, 2024 · 1h 55m
Q2 2024 AI progress analyzed through Four Wars framework: GPU-rich frontier labs (Claude 3.5, Mistral Large), GPU-rich helping GPU-poors (Llama 3.1 synthetic data, Phi 3, Gemma 2), and on-device LL...
1h 55m

Track New Episodes & Guest Appearances

Subscribe to get AI-powered episode summaries, guest detection, and weekly email digests.

Sign Up Free →